INDEX

Explanations

forms of the word "adipiscing" and related terms used in generic placeholder text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ylon

-0.17

riel

-0.16

abay

-0.16

 Ø§ÙĦØ±ÙħØ²ÙĬØ©

-0.14

rence

-0.14

unken

-0.14

enido

-0.14

aru

-0.13

jee

-0.13

 preload

-0.13

POSITIVE LOGITS

/do

0.15

Î½Î·

0.14

ItemAt

0.13

Į¨

0.13

_vocab

0.12

eltas

0.12

/cms

0.12

Äįek

0.12

æ¡Ī

0.12

alt

0.12

Activations Density 0.004%

forms of the word "adipiscing" and related terms used in generic placeholder text

No Comments

No Known Activations